© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 22664
    Prev
    Next
    INDEX
    Explanations

    similarity, sharing, sameness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ugg
    -0.07
    èIJ½èIJ½
    -0.07
    çĻ¾åĢį
    -0.07
    å°¼å°Ķ
    -0.06
    lui
    -0.06
    .Prot
    -0.06
     comporte
    -0.06
     Motel
    -0.06
    ikkert
    -0.06
    Ñħла
    -0.06
    POSITIVE LOGITS
    åħ±äº«
    0.21
     shared
    0.20
    绣ä¸Ģ
    0.19
    Shared
    0.19
     Shared
    0.19
    shared
    0.18
    çļĦ绣ä¸Ģ
    0.17
    åħ±çĶ¨
    0.17
    åIJĮä¸Ģ
    0.17
    çµ±ä¸Ģ
    0.17
    Activations Density 0.456%

    No Known Activations